gpt-oss-120b VRAM and GPU Requirements

gpt-oss-120b needs about 62.49 GB at Q4_K_M with 8K context.

Which GPUs fit

VRAM by quantization

Totals at 8,192 tokens. Q4_K_M is the usual balance of size and quality. FP16 weights are the parameter count times 2 bytes. The FP16 column in the table is the full estimate: weights, cache, and 1 GB.

Context length

Q4_K_M total as the context changes. Cache is the part that grows.

• 2,048 62.28 GB
• 8,192 62.49 GB
• 32,768 63.33 GB
• 131,072 66.71 GB

gpt-oss-120b hardware notes

• Unified memory counts 75 percent of the listed pool as usable. Discrete cards use the full listed memory. The memory column still shows the listed figure.
• Last updated 2025-08-26.
• Weights, cache, and the 1 GB overhead are estimates. How this is calculated.
• Architecture numbers and the parameter count come from the public model record, checked 2026-10-10.
• The published-file row uses a measured byte sum for the weights. Cache and overhead on that row are still estimates.

gpt-oss-120b VRAM FAQ

How much VRAM does gpt-oss-120b need at Q4_K_M?

62.49 GB at 8,192 tokens. Weights are 61.20 GB, the cache is 0.29 GB, and overhead is 1 GB.

Does a 24 GB GPU fit gpt-oss-120b at Q4_K_M?

GeForce RTX 3090 24GB is CPU offload, 38.49 GB over. The quant table uses 8,192 tokens, the smaller of 8,192 and the configured maximum of 131,072.

What context length is configured for gpt-oss-120b?

The configured context length is 131,072 tokens. The quant table uses 8,192 tokens, the smaller of 8,192 and the configured maximum of 131,072.

Which source supplies the parameter count for gpt-oss-120b?

116.8B parameters, from the Hugging Face model record for openai/gpt-oss-120b.

Related models